clip-resource
Warn
Audited by Snyk on Jul 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). At runtime, Step 2 “Retrieve the page or video content directly” and Step 3 “Shape what you fetched” implies the LLM ingests outsider-authored free text fetched from a user-supplied public URL into its context for transformation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata